Tech Lead: AI Compiler & Performance Architect

Black Sesame Technologies Inc; San Jose (CA); On-site; USD 180,000 - 260,000; Full time

Job summary

Black Sesame Technologies Inc. seeks an experienced Tech Lead to steer the design and development of compiler and software infrastructure for AI workloads and heterogeneous ML accelerators.

You will guide architecture, optimization, and production-ready software, collaborating with compiler, runtime, hardware, and ML teams to enable new accelerator capabilities and high-performance systems. The ideal candidate has 8+ years in software engineering, strong C++ background, and proven leadership of

Qualifications

• 8+ years of professional software engineering experience in systems, compilers or performance-critical software.
• Strong proficiency in C++ and solid software engineering fundamentals.
• Experience leading technical projects and mentoring engineers.

Responsibilities

• Lead the technical direction and architecture of compiler and AI software components for ML accelerators.
• Design, implement, and optimize compiler passes and transformations across IR, graph, and backend layers.
• Drive key compiler capabilities such as graph lowering, operator fusion, scheduling, memory planning, code generation, and hardware-specific optimizations.
• Own complex technical problems end-to-end from requirements to production deployment.
• Partner with hardware architects and runtime teams to define software requirements and enable new hardware features.
• Analyze real-world AI/ML workloads to improve performance and memory efficiency.
• Mentor engineers and lead technical initiatives to raise engineering quality.

Skills

C++

Data structures

Algorithms

Software architecture

Team leadership

Performance engineering

Education

Bachelor's or Master’s in CS/CE or related

Tools

MLIR

LLVM

XLA

TVM

Job description

Black Sesame Technologies Inc. seeks an experienced Tech Lead to steer the design and development of compiler and software infrastructure for AI workloads and heterogeneous ML accelerators.

You will guide architecture, optimization, and production-ready software, collaborating with compiler, runtime, hardware, and ML teams to enable new accelerator capabilities and high-performance systems. The ideal candidate has 8+ years in software engineering, strong C++ background, and proven leadership of